pymc-labs

19 mods across 2 repositories, 176 stars between them.

prepare

01

pymc-labs/decision-hub

Command Claude Code

Familiarize yourse with the code in this repository and be ready to discuss it in detail.

97 19d ago A 0 tokens original MIT

pymc-labs/decision-hub

Command Claude Code

End-to-end test of the CLI on the dev environment. Run each step sequentially — stop and report if any step fails.

97 19d ago B 0 tokens original MIT

pymc-labs/decision-hub

Command Claude Code

End-to-end test of publishing a skill with evals on the dev environment. Run each step sequentially — stop and report if any step fails.

97 19d ago C 0 tokens original MIT

pymc-labs/decision-hub

Instructions file

Instructions for pymc-labs/decision-hub, covering project overview, workspace structure, tech stack, development setup and environments (dev / prod / local).

97 19d ago A 4,910 tokens original MIT

my-skill

06

pymc-labs/decision-hub

Skill Claude CodeCodex

Describe what this skill does and how the agent should use it.

97 19d ago A 6 tokens original MIT

dhub-cli

07

pymc-labs/decision-hub

Skill Claude CodeCodex

Guide for using the dhub CLI — the AI skill manager for data science agents. Covers authentication, publishing, installing, running skills, managing API keys, eval reports, and troubleshooting. Use when users ask about dhub commands, skill publishing workflows, or need help with the Decision Hub CLI.

97 19d ago A 63 tokens original MIT

dhub-skill-creator

08

pymc-labs/decision-hub

Skill Claude CodeCodex

Guide for creating effective skills for Claude Code agents. Covers skill design, implementation, validation, packaging, and optionally runtime environments and automated evaluations for Decision Hub publishing. Use when users want to create, improve, or package a skill.

97 19d ago A 53 tokens original MIT

my-skill

09

pymc-labs/decision-hub

Skill Claude CodeCodex

Describe what this skill does and how the agent should use it.

97 19d ago A 6 tokens copy · 100% MIT

my-skill

10

pymc-labs/decision-hub

Skill Claude CodeCodex

Describe what this skill does and how the agent should use it.

97 19d ago A 6 tokens copy · 100% MIT

marimo-notebook

14

pymc-labs/python-analytics-skills

Skill Claude CodeCodex

ALWAYS use when: creating/editing marimo notebooks, working with any .py file containing @app.cell decorators, building reactive Python notebooks, doing exploratory data analysis in notebook form, converting Jupyter (.ipynb) to marimo, or when user mentions "marimo", "reactive notebook", or asks for an interactive…

79 2mo ago A 126 tokens

model-evaluation

15

pymc-labs/python-analytics-skills

Skill Claude CodeCodex

Load when the user is comparing Bayesian models, computing LOO-CV / ELPD, calling arvizstats.loo or arvizstats.compare, doing model stacking/averaging, or computing Bayes factors. Covers the ArviZ 1.1 LOO/ELPD/stacking APIs exclusively (no waic). Triggers include: model comparison, LOO, ELPD, compare, looexpectations…

79 2mo ago A 118 tokens

prior-elicitation

16

pymc-labs/python-analytics-skills

Skill Claude CodeCodex

Load when the user is choosing priors, running prior predictive checks, calling findconstrainedprior, using PreliZ, or otherwise eliciting domain knowledge into a Bayesian model. Covers weakly informative priors, constrained priors, sensitivity analysis, and elicitation workflows. Triggers include: prior selection…

79 2mo ago A 99 tokens

pymc-extras

17

pymc-labs/python-analytics-skills

Skill Claude CodeCodex

Load when the user is working with pymc-extras (pmx) features: splines / BSplineBasis, distributional regression / GAMLSS, R2D2M2CP or horseshoe priors, discrete variable marginalization, or Laplace approximation via fitlaplace. Triggers include: pymcextras, pymc-extras, pmx, splines, BSplineBasis, distributional…

79 2mo ago A 125 tokens

pymc-modeling

18

pymc-labs/python-analytics-skills

Skill Claude CodeCodex

Load whenever the user is working on code that imports pymc, pytensor, or arviz, or asks about Bayesian modeling, MCMC, priors, posteriors, sampling, or model diagnostics. Covers PyMC 6+, PyTensor 3+, ArviZ 1.1+ (DataTree API), pymc-bart, pymc-extras, nutpie, and JAX/NumPyro backends. Use for building probabilistic…

79 2mo ago A 187 tokens

pymc-testing

19

pymc-labs/python-analytics-skills

Skill Claude CodeCodex

Load when writing or modifying pytest tests that touch pymc.Model, pm.sample, or any PyMC model code. Covers pymc.testing.mocksample, pytest fixtures for Bayesian models, and the distinction between fast structure-only tests (mocking) and slow posterior inference tests. Triggers include: testing PyMC, pytest with…

79 2mo ago A 92 tokens